The Model Index
Up to four models

Llama 3.1-70B vs Llama 3

On the index (GPT-4 = 100), Llama 3.1-70B scores 106 and Llama 3 101. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Llama 3.1-70B
Presets
Llama 3.1-70B
10689–122
WeightsOpen
ReleasedJul 2024
Price in / out$0.72 / $0.72
Context131K
Core tests taken1 of 9
Llama 3
10184–118
WeightsOpen
ReleasedApr 2024
Price in / out–
Context–
Core tests taken1 of 9

Llama 3.1-70B and Llama 3 are too close to call (5 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.

Test by testthird-party results

Llama 3.1-70BLlama 3
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MMLU (HELM runs)MMLU (HELM runs)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)AGENTSDTBenchDTBench
Every result as a table
TestLlama 3.1-70BLlama 3
Reasoning & knowledge
GPQA Diamond (Epoch AI)44.2%40.6%
MMLU (HELM runs)80.1%79.3%
Maths
AIME-style maths (OTIS mock)3.6%4.3%
MATH (level 5)36.7%22.6%
Agents
DTBench60.0%54.2%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG